I work on the gap between "the system says X" and "someone needs to safely rely on, question, update, or reverse X." That usually means clinical workflows, coverage or care-navigation decisions, evidence trails, override paths, and just enough structure to catch mistakes and fix them quickly.

U.S. healthcare has spent 15 years moving decisions into software. My work is about making sure responsibility moves with them.

Across every role — molecular biology research, EHR implementation, clinician communication at Doximity, oncology navigation at CancerCompass, care navigation at Transcarent, physician financial support at Andwise — one pattern held: the higher the stakes, the harder it was to trace, question, or undo a decision. So I build toward the gaps where that matters most.

• refract-org/refract — structured change events from Wikipedia revision histories
• zz-plant/stims — live at toil.fyi; 1,868 presets, AI generation, CodeMirror editor, mic/tab input
• zz-plant/whether — weekly operating brief from macro signals for startup leaders
• zz-plant/bread — archive for BREAD, a music party I co-founded in San Francisco
• zz-plant/blog — custom publication and newsletter stack
• zz-plant/sabnzbd-mcp — small MCP server for SABnzbd; stdio, Python, no dependencies
• zz-plant/toolchain-visualizer — Capability Graph: OpenCode capability graph with a Civ-era tech tree; maturity, decay, pathfinding

• Decision records that are useful after the meeting ends.
• Human-in-the-loop systems with real override and repair paths.
• Public knowledge provenance: what changed, when, where, and with what source trail.
• Regulated healthcare workflows where trust depends on clear ownership, timing, and recourse.
• Interfaces that reduce cognitive load instead of moving hidden work onto users and operators.
• AI systems evaluated through artifacts people can inspect, not just benchmarks they can game.

• Early product lead for Doximity Dialer. Patients don't answer calls from unknown numbers — that single observation drove the product. Dialer went on to power 110M+ visits from 300K+ clinicians. iOS reviews climbed from 3.7 to 4.8 stars during my mobile work.
• Co-founded Andwise, a physician financial-wellness company. Raised $240K, grew to 1,200+ physician users and a 700-member community, convened a 50+ physician medical advisory board.
• Led digital products at CancerCompass / CTCA Marketplace, an oncology navigation platform serving 30MM annual visitors. Cut bounce rate 25%, lifted chat conversions 267%.
• Directed care-navigation product at Transcarent across Surgery, Urgent Care, Behavioral Health, and Oncology Care.
• Configured EHR workflows at Epic, where a single misrouted alert could bury a critical lab result. The workflow around the clinician was usually the constraint, not the clinician.
• Studied RNA folding dynamics at Georgia Tech, co-authoring a book chapter in the ACS Symposium Series at 19.
• Mentor, Techstars Northwestern Medicine Healthcare Accelerator.

If you're working on a healthcare AI product that needs to survive real workflow, review, audit, override, and mistakes, I'd like to hear about it.

• kanav@kanav.net
• kanav.net
• github.com/zz-plant